Energy-Based Physics-Informed Form Finding for Clustered Tensegrity Structures

2026-07-14

AI Summary

This work addresses the challenges of strong nonlinearity, stability assurance, and constraint satisfaction in form-finding and physical property prediction for tensegrity structures by proposing an energy-driven physics-informed neural network framework. The method uniquely embeds total potential energy minimization and constitutive relationships directly into the learning objective, enabling simultaneous prediction of equilibrium configurations, member internal forces, and force densities while ensuring physical consistency. By integrating principles of potential energy, constraint-handling mechanisms, and deep learning optimization, the approach achieves scalable form-finding with high data efficiency and robustness. Experimental validation on canonical tensegrity systems—including prismatic and lander-type structures—demonstrates that the method delivers high accuracy, strong generalization capability, and excellent scalability.

Abstract

Tensegrity form-finding and physical property prediction are fundamental inverse problems in structural mechanics, which aim to determine equilibrium configurations and internal force distributions. These problems are challenging due to strong nonlinearity arising from the coupling between geometry and forces, the need to ensure structural stability, and the enforcement of constraints such as boundary conditions and symmetry. Moreover, traditional methods often lack robustness to noise and outliers. This paper proposes an energy-based learning framework for clustered tensegrity form finding and physical property prediction. The proposed approach incorporates total potential energy minimization and constitutive relations into the training objective, enabling the simultaneous prediction of equilibrium nodal configurations and associated physical quantities, including member forces and force densities. By incorporating energy-based physical losses directly into the learning process, the framework improves physical consistency, robustness, and data efficiency. Numerical experiments on tensegrity structures, including prism and lander systems, show the great potential of the proposed approach and demonstrate its capability for scalable form finding and accurate prediction of structural properties.

Problem

• tensegrity form-finding
• physical property prediction
• inverse problems
• structural mechanics
• nonlinearity

Innovation

• energy-based learning
• physics-informed neural networks
• tensegrity form-finding
• potential energy minimization
• physical property prediction